This paper describes a self-modelling, incremental algorithm for learning translation rules from existing bilingual corpora. The notions of supracontext and subcontext are extende...
We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that differe...
A new method for 3D rigid motion estimation is derived under the most general assumption that the measurements are corrupted by inhomogeneous and anisotropic, i.e., heteroscedasti...
The aim of this work is to show the ability of finite-state transducers to simultaneously translate speech into multiple languages. Our proposal deals with an extension of stocha...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...